Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ychampion/cskill-agents --skill forked-skill-execution-with-isolated-contextgit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ychampion/cskill-agents/forked-skill-execution-with-isolated-context)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/forked-skill-execution-with-isolated-context"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/forked-skill-execution-with-isolated-context/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/forked-skill-execution-with-isolated-context"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/forked-skill-execution-with-isolated-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.00511 |
| Opus 5 | $0.00017 | $0.00255 |
| Sonnet 5 | $0.00007 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
forked-skill-execution-with-isolated-context scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Forked Skill Execution With Isolated Context
Domain: agentic-loop
Trigger: Load this skill when SkillTool needs to wrap a prompt command marked with context:'fork' into a sub-agent run that cannot touch the parent session state.
Source Pattern: Distilled from reviewed subagent orchestration, isolation, and lifecycle implementations.
Core Method
Merge the command metadata (model, effort, telemetry tags) into a cloned agent definition, record the forked skill invocation, and run the skill prompt through run agent so it executes in a dedicated loop with its own agent id. Buffer the streaming messages, emit progress when tool content appears, and once run agent completes extract and return a clean result string after releasing the temporary message buffer and invoked-skill state. The parent context still honors overrides (allowed tools, effort, model suffix) via context modifier, while telemetry uses sanitized names and agent IDs so the forked execution is auditable separately.
Key Rules
- Only fork a skill when command context 'fork'; treat every other slash command as inline to avoid extra sub-agents.
- Feed the prepared prompt messages, modified get app state, and context options tools into run agent, tagging emitted messages with tool use id so downstream renderers can tie progress to this tool call.
- Emit progress events for every normalized message that contains
tool_use/tool_resultcontent so UI components can show streaming updates even though SkillTool owns the loop. - After completion, clear invoked skills for the forked agent, compute result text defensively, and include the agent id in the returned tool result so callers can correlate logs or diagnostics.
Example Application
If a CLI-style review skill needs to spawn its own interpreter to run analysis on a repo snapshot, mark it as context:'fork', let SkillTool merge its effort override, and rely on this method to keep the review sub-agent separate while streaming progress back to the caller.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 28 lines · 34 tokens per session scan A ad71b62ac8ec
forked-skill-execution-with-isolated-context is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 511 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.